workflow-planner

workflow-planner is an agent for Claude Code from anatolykoptev/n8n-mcp-agent. It costs 36 tokens per session (1,443 once invoked), scanned A, original, MIT.

An agent that plans n8n automations, where workflows connect services and run steps automatically. It turns a requirement into a proposed trigger, integrations, node structure, credentials, and success criteria.

In plain words
What is it for?
Use it to plan workflows triggered manually, on a schedule, by webhooks, or by app events. It helps design integrations, branching, batching, parallel work, and credential requirements.
Why use it?
It helps clarify an automation before it is built, especially when several services, triggers, or data paths are involved. It can also find related templates for reference.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to plan workflows triggered manually, on a schedule, by webhooks, or by app events. It helps design integrations, branching, batching, parallel work, and credential requirements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/anatolykoptev/n8n-mcp-agent/workflow-planner
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/anatolykoptev/n8n-mcp-agent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for workflow-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/anatolykoptev/n8n-mcp-agent/workflow-planner/github.svg)](https://agentmods.dev/agents/anatolykoptev/n8n-mcp-agent/workflow-planner)
Your own site
<a href="https://agentmods.dev/agents/anatolykoptev/n8n-mcp-agent/workflow-planner"><img src="https://agentmods.dev/badge/agents/anatolykoptev/n8n-mcp-agent/workflow-planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for workflow-planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/anatolykoptev/n8n-mcp-agent/workflow-planner"><img src="https://agentmods.dev/badge/agents/anatolykoptev/n8n-mcp-agent/workflow-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.01443
Opus 5 $0.00018 $0.00722
Sonnet 5 $0.00007 $0.00289
Haiku 4.5 $0.00004 $0.00144

Measured 8d ago against content hash 47d240e941a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

workflow-planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/workflow-planner.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert n8n workflow planner specializing in automation design.

Your Role

  • Analyze automation requirements
  • Search for relevant workflow templates
  • Design optimal node structure
  • Plan credential requirements
  • Identify integration points

Planning Process

1. Requirements Analysis

  • Understand the automation goal
  • Identify trigger type (webhook, schedule, manual)
  • List required integrations (Slack, Telegram, databases, APIs)
  • Define success criteria

2. Template Search

Use n8n-patterns tools to find relevant templates:

n8n-patterns-search query:"[automation type]" category:"[category]"

Categories available:

  • AI Agent Development
  • E-commerce & Retail
  • Marketing Automation
  • Customer Support
  • Data Processing
  • DevOps & CI/CD

3. Trigger Type Selection

Trigger Type Use Case Best For
Manual Testing, development, debugging On-demand execution
Schedule (Cron) Fixed intervals (hourly, daily) Reports, data sync, IoT polling
Webhook Real-time HTTP requests Form submissions, payment events
App-specific Platform events (Gmail, Stripe) Service notifications
Polling Periodic checks for changes When webhooks unavailable

4. Node Organization Patterns

Core Node Categories
Category Nodes Purpose
Flow Control IF, Switch Conditional branching
Data Transform Set, Edit Fields, Code Create/modify data fields
Merging Merge, Compare Datasets Combine multiple streams
Looping Loop Over Items Batch processing, rate limits
Timing Wait Delays, rate limiting
Error Handling Stop And Error, Error Trigger Exception management
Standard Workflow Structure
[Trigger] → [Input Validation] → [Business Logic] → [Output/Notification]

Common patterns:

  • Webhook → Process → Respond: API endpoint automation
  • Schedule → Fetch → Transform → Store: Data sync
  • Trigger → Condition → Branch A / Branch B: Conditional logic
  • Trigger → Loop → Process Each: Batch processing

Read the full file on GitHub · 194 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 194 lines · 36 tokens per session scan A 47d240e941a2

Subscribe to this mod's changes

workflow-planner is an agent published in the GitHub repository anatolykoptev/n8n-mcp-agent (0 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,443 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

workflow-reviewer

Code review and error diagnosis for n8nac Decorator-TS workflow files. Use after writing or modifying .workflow.ts files to catch issues before pushing. Run in background for non-blocking reviews.

neurawork-git/n8n-autopilot · 45 tokens

n8n-stack-architect

Decomposes a PRP-style end-to-end use case into a stack of sub-workflows along known decomposition rules, fixes the handover contracts between them, and (in EXTEND mode) plans the delta against an already-comprehended stack. Read-only — emits the stack plan / delta, never writes files or touches the instance. Used as…

neurawork-git/n8n-autopilot · 94 tokens

n8n-stack-comprehender

Reconstructs the real call-graph (DAG) of an existing workflow stack from executeWorkflow references in the local mirror, reconciles it against the central architecture doc (or reverse-engineers one if absent), and reports the current stack shape so the architect can plan a delta. Read-only — assumes the local repo…

neurawork-git/n8n-autopilot · 100 tokens

n8n-tester

Run the test-phase n8nac commands the orchestrator asks for and map the real output to the requested schema. You do not edit files.

neurawork-git/n8n-autopilot · 92 tokens

n8n-author

Writes or edits an n8n Decorator-TS .workflow.ts file from verified node contracts, or fixes a file from validation/wiring errors. The only file-writing agent in the build-workflow-v2 pipeline. Never validates or pushes — the orchestrator gates that.

neurawork-git/n8n-autopilot · 60 tokens

feedback-triage

Maintainer-side triage of the open feedback-labelled issues on the public plugin repo (one issue per finding, created by the ingest webhook). Dedups issues that describe the same underlying problem (closes duplicates with a cross-reference), tightens titles, adds severity/priority context as a comment, and produces a…

neurawork-git/n8n-autopilot · 95 tokens